发表机构
Goertek Alpha Labs（歌尔Alpha实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出StereoGaussians，从单个立体图像对前馈预测度量3DGS表示，通过复用预训练立体网络特征与视差锚定几何，并增设高斯层和扩展画布处理遮挡与视野外内容，在立体基准上超越强基线。
AI 中文摘要
前馈三维高斯泼溅（3DGS）能够在无需逐场景优化的情况下进行重建，但实际的立体相机应用需要超出输入视图的近邻视图外推。立体深度锚定了可见表面，然而渲染新暴露区域还需要学习外观和额外的场景容量。我们提出了StereoGaussians，它从单个已标定的立体图像对预测度量三维高斯泼溅表示。该方法重用冻结的预训练立体网络的中间表示来预测高斯属性，同时已标定的视差锚定几何。第二层高斯层和扩展的图像画布为被遮挡区域和视野外内容提供了容量。在训练方面，我们从质量过滤的3DGS教师构建了SceneSplat-Stereo数据集，将立体输入与803个训练场景中的近邻目标视图配对。在未见过的真实和逼真立体基准上的实验表明，该方法优于强视图合成基线，而消融研究支持了我们的主要设计选择。
英文摘要
Feed-forward 3D Gaussian Splatting (3DGS) enables reconstruction without per- scene optimisation, but practical stereo-camera applications require nearby-view extrapolation beyond the input views. Stereo depth anchors visible surfaces, yet rendering newly exposed regions also requires learned appearance and additional scene capacity. We introduce StereoGaussians, which predicts a metric 3DGS representation from a single calibrated stereo pair. It reuses intermediate repre- sentations from frozen pretrained stereo networks to predict Gaussian attributes, while calibrated disparity anchors the geometry. A second Gaussian layer and an expanded image canvas provide capacity for disoccluded and outside-field-of- view content. For training, we construct SceneSplat-Stereo from quality-filtered 3DGS teachers, pairing stereo inputs with nearby target views across 803 training scenes. Experiments on unseen real and photorealistic stereo benchmarks demon- strate improvements over strong view-synthesis baselines, while ablation studies support our main design choices.
